# This set of tests is for UTF-16 and UTF-32 support, and is relevant only to # the 16-bit and 32-bit libraries. The output is different for each library, # so there are separate output files. /ÃÃÃxxx/IB,utf,no_utf_check ** Failed: invalid UTF-8 string cannot be converted to 16-bit string /abc/utf Ã] ** Failed: invalid UTF-8 string cannot be used as input in UTF mode /X(\C{3})/utf X\x{11234}Y 0: X\x{11234}Y 1: \x{11234}Y X\x{11234}YZ 0: X\x{11234}Y 1: \x{11234}Y /X(\C{4})/utf X\x{11234}YZ 0: X\x{11234}YZ 1: \x{11234}YZ X\x{11234}YZW 0: X\x{11234}YZ 1: \x{11234}YZ /X\C*/utf XYZabcdce 0: XYZabcdce /X\C*?/utf XYZabcde 0: X /X\C{3,5}/utf Xabcdefg 0: Xabcde X\x{11234}Y 0: X\x{11234}Y X\x{11234}YZ 0: X\x{11234}YZ X\x{11234}\x{512} 0: X\x{11234}\x{512} X\x{11234}\x{512}YZ 0: X\x{11234}\x{512}YZ X\x{11234}\x{512}\x{11234}Z 0: X\x{11234}\x{512}\x{11234} /X\C{3,5}?/utf Xabcdefg 0: Xabc X\x{11234}Y 0: X\x{11234}Y X\x{11234}YZ 0: X\x{11234}Y X\x{11234}\x{512}YZ 0: X\x{11234}\x{512} *** Failers No match X\x{11234} No match /a\Cb/utf aXb 0: aXb a\nb 0: a\x{0a}b /a\C\Cb/utf a\x{12257}b 0: a\x{12257}b a\x{12257}\x{11234}b No match ** Failers No match a\x{100}b No match /ab\Cde/utf abXde 0: abXde # Check maximum character size /\x{ffff}/IB,utf ------------------------------------------------------------------ Bra \x{ffff} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{ffff} No last code unit Subject length lower bound = 1 /\x{10000}/IB,utf ------------------------------------------------------------------ Bra \x{10000} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{d800} Last code unit = \x{dc00} Subject length lower bound = 1 /\x{100}/IB,utf ------------------------------------------------------------------ Bra \x{100} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{100} No last code unit Subject length lower bound = 1 /\x{1000}/IB,utf ------------------------------------------------------------------ Bra \x{1000} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{1000} No last code unit Subject length lower bound = 1 /\x{10000}/IB,utf ------------------------------------------------------------------ Bra \x{10000} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{d800} Last code unit = \x{dc00} Subject length lower bound = 1 /\x{100000}/IB,utf ------------------------------------------------------------------ Bra \x{100000} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{dbc0} Last code unit = \x{dc00} Subject length lower bound = 1 /\x{10ffff}/IB,utf ------------------------------------------------------------------ Bra \x{10ffff} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{dbff} Last code unit = \x{dfff} Subject length lower bound = 1 /[\x{ff}]/IB,utf ------------------------------------------------------------------ Bra \x{ff} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \xff No last code unit Subject length lower bound = 1 /[\x{100}]/IB,utf ------------------------------------------------------------------ Bra \x{100} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{100} No last code unit Subject length lower bound = 1 /\x80/IB,utf ------------------------------------------------------------------ Bra \x{80} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x80 No last code unit Subject length lower bound = 1 /\xff/IB,utf ------------------------------------------------------------------ Bra \x{ff} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \xff No last code unit Subject length lower bound = 1 /\x{D55c}\x{ad6d}\x{C5B4}/IB,utf ------------------------------------------------------------------ Bra \x{d55c}\x{ad6d}\x{c5b4} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{d55c} Last code unit = \x{c5b4} Subject length lower bound = 3 \x{D55c}\x{ad6d}\x{C5B4} 0: \x{d55c}\x{ad6d}\x{c5b4} /\x{65e5}\x{672c}\x{8a9e}/IB,utf ------------------------------------------------------------------ Bra \x{65e5}\x{672c}\x{8a9e} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{65e5} Last code unit = \x{8a9e} Subject length lower bound = 3 \x{65e5}\x{672c}\x{8a9e} 0: \x{65e5}\x{672c}\x{8a9e} /\x{80}/IB,utf ------------------------------------------------------------------ Bra \x{80} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x80 No last code unit Subject length lower bound = 1 /\x{084}/IB,utf ------------------------------------------------------------------ Bra \x{84} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x84 No last code unit Subject length lower bound = 1 /\x{104}/IB,utf ------------------------------------------------------------------ Bra \x{104} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{104} No last code unit Subject length lower bound = 1 /\x{861}/IB,utf ------------------------------------------------------------------ Bra \x{861} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{861} No last code unit Subject length lower bound = 1 /\x{212ab}/IB,utf ------------------------------------------------------------------ Bra \x{212ab} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{d844} Last code unit = \x{deab} Subject length lower bound = 1 # This one is here not because it's different to Perl, but because the way # the captured single-byte is displayed. (In Perl it becomes a character, and you # can't tell the difference.) /X(\C)(.*)/utf X\x{1234} 0: X\x{1234} 1: \x{1234} 2: X\nabc 0: X\x{0a}abc 1: \x{0a} 2: abc # This one is here because Perl gives out a grumbly error message (quite # correctly, but that messes up comparisons). /a\Cb/utf *** Failers No match a\x{100}b 0: a\x{100}b /[^ab\xC0-\xF0]/IB,utf ------------------------------------------------------------------ Bra [\x00-`c-\xbf\xf1-\xff] (neg) Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 9 : ; < = > ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y Z [ \ ] ^ _ ` c d e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f \x80 \x81 \x82 \x83 \x84 \x85 \x86 \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 \x93 \x94 \x95 \x96 \x97 \x98 \x99 \x9a \x9b \x9c \x9d \x9e \x9f \xa0 \xa1 \xa2 \xa3 \xa4 \xa5 \xa6 \xa7 \xa8 \xa9 \xaa \xab \xac \xad \xae \xaf \xb0 \xb1 \xb2 \xb3 \xb4 \xb5 \xb6 \xb7 \xb8 \xb9 \xba \xbb \xbc \xbd \xbe \xbf \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd \xfe \xff No last code unit Subject length lower bound = 1 \x{f1} 0: \x{f1} \x{bf} 0: \x{bf} \x{100} 0: \x{100} \x{1000} 0: \x{1000} *** Failers 0: * \x{c0} No match \x{f0} No match /Ä€{3,4}/IB,utf ------------------------------------------------------------------ Bra \x{100}{3} \x{100}?+ Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{100} Last code unit = \x{100} Subject length lower bound = 3 \x{100}\x{100}\x{100}\x{100\x{100} 0: \x{100}\x{100}\x{100} /(\x{100}+|x)/IB,utf ------------------------------------------------------------------ Bra CBra 1 \x{100}++ Alt x Ket Ket End ------------------------------------------------------------------ Capturing subpattern count = 1 Options: utf Starting code units: x \xff No last code unit Subject length lower bound = 1 /(\x{100}*a|x)/IB,utf ------------------------------------------------------------------ Bra CBra 1 \x{100}*+ a Alt x Ket Ket End ------------------------------------------------------------------ Capturing subpattern count = 1 Options: utf Starting code units: a x \xff No last code unit Subject length lower bound = 1 /(\x{100}{0,2}a|x)/IB,utf ------------------------------------------------------------------ Bra CBra 1 \x{100}{0,2}+ a Alt x Ket Ket End ------------------------------------------------------------------ Capturing subpattern count = 1 Options: utf Starting code units: a x \xff No last code unit Subject length lower bound = 1 /(\x{100}{1,2}a|x)/IB,utf ------------------------------------------------------------------ Bra CBra 1 \x{100} \x{100}{0,1}+ a Alt x Ket Ket End ------------------------------------------------------------------ Capturing subpattern count = 1 Options: utf Starting code units: x \xff No last code unit Subject length lower bound = 1 /\x{100}/IB,utf ------------------------------------------------------------------ Bra \x{100} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{100} No last code unit Subject length lower bound = 1 /a\x{100}\x{101}*/IB,utf ------------------------------------------------------------------ Bra a\x{100} \x{101}*+ Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = 'a' Last code unit = \x{100} Subject length lower bound = 2 /a\x{100}\x{101}+/IB,utf ------------------------------------------------------------------ Bra a\x{100} \x{101}++ Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = 'a' Last code unit = \x{101} Subject length lower bound = 3 /[^\x{c4}]/IB ------------------------------------------------------------------ Bra [^\x{c4}] Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 No options No first code unit No last code unit Subject length lower bound = 1 /[\x{100}]/IB,utf ------------------------------------------------------------------ Bra \x{100} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{100} No last code unit Subject length lower bound = 1 \x{100} 0: \x{100} Z\x{100} 0: \x{100} \x{100}Z 0: \x{100} *** Failers No match /[\xff]/IB,utf ------------------------------------------------------------------ Bra \x{ff} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \xff No last code unit Subject length lower bound = 1 >\x{ff}< 0: \x{ff} /[^\xff]/IB,utf ------------------------------------------------------------------ Bra [^\x{ff}] Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf No first code unit No last code unit Subject length lower bound = 1 /\x{100}abc(xyz(?1))/IB,utf ------------------------------------------------------------------ Bra \x{100}abc CBra 1 xyz Recurse Ket Ket End ------------------------------------------------------------------ Capturing subpattern count = 1 Options: utf First code unit = \x{100} Last code unit = 'z' Subject length lower bound = 7 /\777/I,utf Capturing subpattern count = 0 Options: utf First code unit = \x{1ff} No last code unit Subject length lower bound = 1 \x{1ff} 0: \x{1ff} \777 0: \x{1ff} /\x{100}+\x{200}/IB,utf ------------------------------------------------------------------ Bra \x{100}++ \x{200} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{100} Last code unit = \x{200} Subject length lower bound = 2 /\x{100}+X/IB,utf ------------------------------------------------------------------ Bra \x{100}++ X Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = \x{100} Last code unit = 'X' Subject length lower bound = 2 /^[\QÄ€\E-\QÅ\E/B,utf Failed: error 106 at offset 13: missing terminating ] for character class /X/utf \x{d800} Failed: error -24: UTF-16 error: missing low surrogate at end \x{d800}\=no_utf_check No match \x{da00} Failed: error -24: UTF-16 error: missing low surrogate at end \x{da00}\=no_utf_check No match \x{dc00} Failed: error -26: UTF-16 error: isolated low surrogate \x{dc00}\=no_utf_check No match \x{de00} Failed: error -26: UTF-16 error: isolated low surrogate \x{de00}\=no_utf_check No match \x{dfff} Failed: error -26: UTF-16 error: isolated low surrogate \x{dfff}\=no_utf_check No match \x{110000} ** Failed: character \x{110000} is greater than 0x10ffff and so cannot be converted to UTF-16 \x{d800}\x{1234} Failed: error -25: UTF-16 error: invalid low surrogate /(*UTF16)\x{11234}/ abcd\x{11234}pqr 0: \x{11234} /(*UTF)\x{11234}/I Capturing subpattern count = 0 Compile options: Overall options: utf First code unit = \x{d804} Last code unit = \x{de34} Subject length lower bound = 1 abcd\x{11234}pqr 0: \x{11234} /(*UTF-32)\x{11234}/ Failed: error 160 at offset 5: (*VERB) not recognized or malformed abcd\x{11234}pqr /(*CRLF)(*UTF16)(*BSR_UNICODE)a\Rb/I Capturing subpattern count = 0 Compile options: Overall options: utf Forced newline is CRLF First code unit = 'a' Last code unit = 'b' Subject length lower bound = 3 /(*CRLF)(*UTF32)(*BSR_UNICODE)a\Rb/I Failed: error 160 at offset 12: (*VERB) not recognized or malformed /\h/I,utf Capturing subpattern count = 0 Options: utf Starting code units: \x09 \x20 \xa0 \xff No last code unit Subject length lower bound = 1 ABC\x{09} 0: \x{09} ABC\x{20} 0: ABC\x{a0} 0: \x{a0} ABC\x{1680} 0: \x{1680} ABC\x{180e} 0: \x{180e} ABC\x{2000} 0: \x{2000} ABC\x{202f} 0: \x{202f} ABC\x{205f} 0: \x{205f} ABC\x{3000} 0: \x{3000} /\v/I,utf Capturing subpattern count = 0 Options: utf Starting code units: \x0a \x0b \x0c \x0d \x85 \xff No last code unit Subject length lower bound = 1 ABC\x{0a} 0: \x{0a} ABC\x{0b} 0: \x{0b} ABC\x{0c} 0: \x{0c} ABC\x{0d} 0: \x{0d} ABC\x{85} 0: \x{85} ABC\x{2028} 0: \x{2028} /\h*A/I,utf Capturing subpattern count = 0 Options: utf Starting code units: \x09 \x20 A \xa0 \xff Last code unit = 'A' Subject length lower bound = 1 CDBABC 0: A \x{2000}ABC 0: \x{2000}A /\R*A/I,bsr=unicode,utf Capturing subpattern count = 0 Options: utf Starting code units: \x0a \x0b \x0c \x0d A \x85 \xff Last code unit = 'A' Subject length lower bound = 1 CDBABC 0: A \x{2028}A 0: \x{2028}A /\v+A/I,utf Capturing subpattern count = 0 Options: utf Starting code units: \x0a \x0b \x0c \x0d \x85 \xff Last code unit = 'A' Subject length lower bound = 2 /\s?xxx\s/I,utf Capturing subpattern count = 0 Options: utf Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 x Last code unit = 'x' Subject length lower bound = 4 /\sxxx\s/I,utf,tables=2 Capturing subpattern count = 0 Options: utf Starting code units: \x09 \x0a \x0b \x0c \x0d \x20 \x85 \xa0 Last code unit = 'x' Subject length lower bound = 5 AB\x{85}xxx\x{a0}XYZ 0: \x{85}xxx\x{a0} AB\x{a0}xxx\x{85}XYZ 0: \x{a0}xxx\x{85} /\S \S/I,utf,tables=2 Capturing subpattern count = 0 Options: utf Starting code units: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d \x1e \x1f ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 9 : ; < = > ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y Z [ \ ] ^ _ ` a b c d e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f \x80 \x81 \x82 \x83 \x84 \x86 \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 \x93 \x94 \x95 \x96 \x97 \x98 \x99 \x9a \x9b \x9c \x9d \x9e \x9f \xa1 \xa2 \xa3 \xa4 \xa5 \xa6 \xa7 \xa8 \xa9 \xaa \xab \xac \xad \xae \xaf \xb0 \xb1 \xb2 \xb3 \xb4 \xb5 \xb6 \xb7 \xb8 \xb9 \xba \xbb \xbc \xbd \xbe \xbf \xc0 \xc1 \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd \xfe \xff Last code unit = ' ' Subject length lower bound = 3 \x{a2} \x{84} 0: \x{a2} \x{84} A Z 0: A Z /a+/utf a\x{123}aa\=offset=1 0: aa a\x{123}aa\=offset=2 0: aa a\x{123}aa\=offset=3 0: a a\x{123}aa\=offset=4 No match a\x{123}aa\=offset=5 Failed: error -34: bad offset value a\x{123}aa\=offset=6 Failed: error -34: bad offset value /\x{1234}+/Ii,utf Capturing subpattern count = 0 Options: caseless utf First code unit = \x{1234} No last code unit Subject length lower bound = 1 /\x{1234}+?/Ii,utf Capturing subpattern count = 0 Options: caseless utf First code unit = \x{1234} No last code unit Subject length lower bound = 1 /\x{1234}++/Ii,utf Capturing subpattern count = 0 Options: caseless utf First code unit = \x{1234} No last code unit Subject length lower bound = 1 /\x{1234}{2}/Ii,utf Capturing subpattern count = 0 Options: caseless utf First code unit = \x{1234} Last code unit = \x{1234} Subject length lower bound = 2 /[^\x{c4}]/IB,utf ------------------------------------------------------------------ Bra [^\x{c4}] Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf No first code unit No last code unit Subject length lower bound = 1 /X+\x{200}/IB,utf ------------------------------------------------------------------ Bra X++ \x{200} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = 'X' Last code unit = \x{200} Subject length lower bound = 2 /\R/I,utf Capturing subpattern count = 0 Options: utf Starting code units: \x0a \x0b \x0c \x0d \x85 \xff No last code unit Subject length lower bound = 1 # Check bad offset /a/utf \x{10000}\=offset=1 Error -36 (bad UTF-16 offset) \x{10000}ab\=offset=1 Error -36 (bad UTF-16 offset) \x{10000}ab\=offset=2 0: a \x{10000}ab\=offset=3 No match \x{10000}ab\=offset=4 No match \x{10000}ab\=offset=5 Failed: error -34: bad offset value /í¼€/utf Failed: error -26 at offset 0: UTF-16 error: isolated low surrogate /\w+\x{C4}/B,utf ------------------------------------------------------------------ Bra \w++ \x{c4} Ket End ------------------------------------------------------------------ a\x{C4}\x{C4} 0: a\x{c4} /\w+\x{C4}/B,utf,tables=2 ------------------------------------------------------------------ Bra \w+ \x{c4} Ket End ------------------------------------------------------------------ a\x{C4}\x{C4} 0: a\x{c4}\x{c4} /\W+\x{C4}/B,utf ------------------------------------------------------------------ Bra \W+ \x{c4} Ket End ------------------------------------------------------------------ !\x{C4} 0: !\x{c4} /\W+\x{C4}/B,utf,tables=2 ------------------------------------------------------------------ Bra \W++ \x{c4} Ket End ------------------------------------------------------------------ !\x{C4} 0: !\x{c4} /\W+\x{A1}/B,utf ------------------------------------------------------------------ Bra \W+ \x{a1} Ket End ------------------------------------------------------------------ !\x{A1} 0: !\x{a1} /\W+\x{A1}/B,utf,tables=2 ------------------------------------------------------------------ Bra \W+ \x{a1} Ket End ------------------------------------------------------------------ !\x{A1} 0: !\x{a1} /X\s+\x{A0}/B,utf ------------------------------------------------------------------ Bra X \s++ \x{a0} Ket End ------------------------------------------------------------------ X\x20\x{A0}\x{A0} 0: X \x{a0} /X\s+\x{A0}/B,utf,tables=2 ------------------------------------------------------------------ Bra X \s+ \x{a0} Ket End ------------------------------------------------------------------ X\x20\x{A0}\x{A0} 0: X \x{a0}\x{a0} /\S+\x{A0}/B,utf ------------------------------------------------------------------ Bra \S+ \x{a0} Ket End ------------------------------------------------------------------ X\x{A0}\x{A0} 0: X\x{a0}\x{a0} /\S+\x{A0}/B,utf,tables=2 ------------------------------------------------------------------ Bra \S++ \x{a0} Ket End ------------------------------------------------------------------ X\x{A0}\x{A0} 0: X\x{a0} /\x{a0}+\s!/B,utf ------------------------------------------------------------------ Bra \x{a0}++ \s ! Ket End ------------------------------------------------------------------ \x{a0}\x20! 0: \x{a0} ! /\x{a0}+\s!/B,utf,tables=2 ------------------------------------------------------------------ Bra \x{a0}+ \s ! Ket End ------------------------------------------------------------------ \x{a0}\x20! 0: \x{a0} ! /(*UTF)abc/never_utf Failed: error 174 at offset 6: using UTF is disabled by the application /abc/utf,never_utf Failed: error 174 at offset 0: using UTF is disabled by the application /A\x{391}\x{10427}\x{ff3a}\x{1fb0}/IBi,utf ------------------------------------------------------------------ Bra /i A\x{391}\x{10427}\x{ff3a}\x{1fb0} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: caseless utf First code unit = 'A' (caseless) Last code unit = \x{1fb0} (caseless) Subject length lower bound = 5 /A\x{391}\x{10427}\x{ff3a}\x{1fb0}/IB,utf ------------------------------------------------------------------ Bra A\x{391}\x{10427}\x{ff3a}\x{1fb0} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = 'A' Last code unit = \x{1fb0} Subject length lower bound = 5 /AB\x{1fb0}/IB,utf ------------------------------------------------------------------ Bra AB\x{1fb0} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: utf First code unit = 'A' Last code unit = \x{1fb0} Subject length lower bound = 3 /AB\x{1fb0}/IBi,utf ------------------------------------------------------------------ Bra /i AB\x{1fb0} Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 Options: caseless utf First code unit = 'A' (caseless) Last code unit = \x{1fb0} (caseless) Subject length lower bound = 3 /\x{401}\x{420}\x{421}\x{422}\x{423}\x{424}\x{425}\x{426}\x{427}\x{428}\x{429}\x{42a}\x{42b}\x{42c}\x{42d}\x{42e}\x{42f}/Ii,utf Capturing subpattern count = 0 Options: caseless utf First code unit = \x{401} (caseless) Last code unit = \x{42f} (caseless) Subject length lower bound = 17 \x{401}\x{420}\x{421}\x{422}\x{423}\x{424}\x{425}\x{426}\x{427}\x{428}\x{429}\x{42a}\x{42b}\x{42c}\x{42d}\x{42e}\x{42f} 0: \x{401}\x{420}\x{421}\x{422}\x{423}\x{424}\x{425}\x{426}\x{427}\x{428}\x{429}\x{42a}\x{42b}\x{42c}\x{42d}\x{42e}\x{42f} \x{451}\x{440}\x{441}\x{442}\x{443}\x{444}\x{445}\x{446}\x{447}\x{448}\x{449}\x{44a}\x{44b}\x{44c}\x{44d}\x{44e}\x{44f} 0: \x{451}\x{440}\x{441}\x{442}\x{443}\x{444}\x{445}\x{446}\x{447}\x{448}\x{449}\x{44a}\x{44b}\x{44c}\x{44d}\x{44e}\x{44f} /[â±¥]/Bi,utf ------------------------------------------------------------------ Bra /i \x{2c65} Ket End ------------------------------------------------------------------ /[^â±¥]/Bi,utf ------------------------------------------------------------------ Bra /i [^\x{2c65}] Ket End ------------------------------------------------------------------ /[[:blank:]]/B,ucp ------------------------------------------------------------------ Bra [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}] Ket End ------------------------------------------------------------------ /\x{212a}+/Ii,utf Capturing subpattern count = 0 Options: caseless utf Starting code units: K k \xff No last code unit Subject length lower bound = 1 KKkk\x{212a} 0: KKkk\x{212a} /s+/Ii,utf Capturing subpattern count = 0 Options: caseless utf Starting code units: S s \xff No last code unit Subject length lower bound = 1 SSss\x{17f} 0: SSss\x{17f} # Non-UTF characters should give errors in both 16-bit and 32-bit modes. /\x{110000}/utf Failed: error 134 at offset 9: character code point value in \x{} or \o{} is too large /\o{4200000}/utf Failed: error 134 at offset 10: character code point value in \x{} or \o{} is too large /\C/utf \x{110000} ** Failed: character \x{110000} is greater than 0x10ffff and so cannot be converted to UTF-16 # End of testinput12